Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 102 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.9422. Min Act: -0.1700
Data Index: 659138 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8946. Min Act: -0.1700
Data Index: 721874 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8629. Min Act: -0.1700
Data Index: 425466 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8470. Min Act: -0.1700
Data Index: 600782 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8470. Min Act: -0.1700
Data Index: 871004 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8629. Min Act: -0.1700
Data Index: 390191 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8629. Min Act: -0.1700
Data Index: 182507 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8311. Min Act: -0.1700
Data Index: 493743 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8470. Min Act: -0.1700
Data Index: 874308 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8311. Min Act: -0.1700
Data Index: 1278085 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8311. Min Act: -0.1700
Data Index: 947366 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8311. Min Act: -0.1700
Data Index: 960554 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.8152. Min Act: -0.1700
Data Index: 307258 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 194457 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7833. Min Act: -0.1700
Data Index: 293938 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 5199 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 202657 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 870057 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 898085 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9422. Min Range: -2.9422
Max Act: 2.7992. Min Act: -0.1700
Data Index: 777806 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19